
import math
import geopandas as gpd
import pandas as pd
from fiona.crs import from_epsg # 좌표변환 
import contextily as ctx 
# 거리를 계산하기 위한 라이브러리 로드
from geopy.distance import great_circle


import matplotlib
import matplotlib.pyplot as plt
import matplotlib as mpl
import seaborn as sns

%matplotlib inline
%config InlineBackend.figure_format = 'retina'
sns.set_style('darkgrid') #whitegrid, dark, white, ticks
mpl.rc('font', family='NanumGothic') #한글 폰트 적용시
plt.rcParams["figure.figsize"] = (16,4.5) #차트 사이즈


df_mart01 = pd.read_csv('data/서울특별시 대규모점포 인허가 정보.csv', encoding='cp949')
df_mart01.info()
df_mart01.head(2)

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 937 entries, 0 to 936
Data columns (total 26 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   개방자치단체코드  937 non-null    int64  
 1   관리번호      937 non-null    int64  
 2   인허가일자     937 non-null    int64  
 3   인허가취소일자   7 non-null      float64
 4   영업상태코드    937 non-null    int64  
 5   영업상태명     937 non-null    object 
 6   상세영업상태코드  937 non-null    object 
 7   상세영업상태명   929 non-null    object 
 8   폐업일자      143 non-null    float64
 9   휴업시작일자    17 non-null     float64
 10  휴업종료일자    17 non-null     float64
 11  재개업일자     34 non-null     float64
 12  전화번호      922 non-null    object 
 13  소재지면적     862 non-null    float64
 14  소재지우편번호   408 non-null    float64
 15  지번주소      815 non-null    object 
 16  도로명주소     762 non-null    object 
 17  도로명우편번호   581 non-null    float64
 18  사업장명      937 non-null    object 
 19  최종수정일자    937 non-null    int64  
 20  데이터갱신구분   937 non-null    object 
 21  데이터갱신일자   937 non-null    object 
 22  업태구분명     933 non-null    object 
 23  좌표정보(X)   863 non-null    float64
 24  좌표정보(Y)   863 non-null    float64
 25  점포구분명     559 non-null    object 
dtypes: float64(10), int64(5), object(11)
memory usage: 190.5+ KB


# 정상영업중인 대규모점포만 추출
df_mart02 = df_mart01[ (df_mart01.영업상태코드 == 1)  ]  #& (df_mart01.업태구분명.isin(['대형마트', '쇼핑센터', '백화점'])
df_mart02.info()
df_mart02.head(2)

<class 'pandas.core.frame.DataFrame'>
Int64Index: 707 entries, 0 to 936
Data columns (total 26 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   개방자치단체코드  707 non-null    int64  
 1   관리번호      707 non-null    int64  
 2   인허가일자     707 non-null    int64  
 3   인허가취소일자   0 non-null      float64
 4   영업상태코드    707 non-null    int64  
 5   영업상태명     707 non-null    object 
 6   상세영업상태코드  707 non-null    object 
 7   상세영업상태명   699 non-null    object 
 8   폐업일자      0 non-null      float64
 9   휴업시작일자    4 non-null      float64
 10  휴업종료일자    4 non-null      float64
 11  재개업일자     32 non-null     float64
 12  전화번호      699 non-null    object 
 13  소재지면적     652 non-null    float64
 14  소재지우편번호   335 non-null    float64
 15  지번주소      608 non-null    object 
 16  도로명주소     626 non-null    object 
 17  도로명우편번호   498 non-null    float64
 18  사업장명      707 non-null    object 
 19  최종수정일자    707 non-null    int64  
 20  데이터갱신구분   707 non-null    object 
 21  데이터갱신일자   707 non-null    object 
 22  업태구분명     706 non-null    object 
 23  좌표정보(X)   657 non-null    float64
 24  좌표정보(Y)   657 non-null    float64
 25  점포구분명     449 non-null    object 
dtypes: float64(10), int64(5), object(11)
memory usage: 149.1+ KB


# 소재지면적과 좌표가 있는 데이터만 사용 
df_mart02.dropna(subset=['소재지면적'], axis=0, inplace=True)
df_mart02.dropna(subset=['좌표정보(X)'], axis=0, inplace=True)
df_mart02.dropna(subset=['좌표정보(Y)'], axis=0, inplace=True)
df_mart02.reset_index()
df_mart02.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 637 entries, 0 to 936
Data columns (total 26 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   개방자치단체코드  637 non-null    int64  
 1   관리번호      637 non-null    int64  
 2   인허가일자     637 non-null    int64  
 3   인허가취소일자   0 non-null      float64
 4   영업상태코드    637 non-null    int64  
 5   영업상태명     637 non-null    object 
 6   상세영업상태코드  637 non-null    object 
 7   상세영업상태명   632 non-null    object 
 8   폐업일자      0 non-null      float64
 9   휴업시작일자    4 non-null      float64
 10  휴업종료일자    4 non-null      float64
 11  재개업일자     28 non-null     float64
 12  전화번호      632 non-null    object 
 13  소재지면적     637 non-null    float64
 14  소재지우편번호   330 non-null    float64
 15  지번주소      541 non-null    object 
 16  도로명주소     607 non-null    object 
 17  도로명우편번호   492 non-null    float64
 18  사업장명      637 non-null    object 
 19  최종수정일자    637 non-null    int64  
 20  데이터갱신구분   637 non-null    object 
 21  데이터갱신일자   637 non-null    object 
 22  업태구분명     636 non-null    object 
 23  좌표정보(X)   637 non-null    float64
 24  좌표정보(Y)   637 non-null    float64
 25  점포구분명     441 non-null    object 
dtypes: float64(10), int64(5), object(11)
memory usage: 134.4+ KB

<ipython-input-127-b550982e086b>:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_mart02.dropna(subset=['소재지면적'], axis=0, inplace=True)
<ipython-input-127-b550982e086b>:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_mart02.dropna(subset=['좌표정보(X)'], axis=0, inplace=True)
<ipython-input-127-b550982e086b>:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_mart02.dropna(subset=['좌표정보(Y)'], axis=0, inplace=True)


df_mart02.소재지면적.describe()

count       637.000000
mean       9054.809937
std       15856.622852
min           0.000000
25%         476.000000
50%        3386.040000
75%       10269.890000
max      145244.540000
Name: 소재지면적, dtype: float64


#소재지면적 평균이 약 9000, 중위값이 3386으로 소규모 매장이 많이 포함되어 있음. 상위 75% 보다 큰 매장만 추출
df_mart02 = df_mart02[ df_mart02.소재지면적 >= 10270 ]  
df_mart02.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 159 entries, 0 to 935
Data columns (total 26 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   개방자치단체코드  159 non-null    int64  
 1   관리번호      159 non-null    int64  
 2   인허가일자     159 non-null    int64  
 3   인허가취소일자   0 non-null      float64
 4   영업상태코드    159 non-null    int64  
 5   영업상태명     159 non-null    object 
 6   상세영업상태코드  159 non-null    object 
 7   상세영업상태명   157 non-null    object 
 8   폐업일자      0 non-null      float64
 9   휴업시작일자    2 non-null      float64
 10  휴업종료일자    2 non-null      float64
 11  재개업일자     7 non-null      float64
 12  전화번호      159 non-null    object 
 13  소재지면적     159 non-null    float64
 14  소재지우편번호   85 non-null     float64
 15  지번주소      143 non-null    object 
 16  도로명주소     153 non-null    object 
 17  도로명우편번호   114 non-null    float64
 18  사업장명      159 non-null    object 
 19  최종수정일자    159 non-null    int64  
 20  데이터갱신구분   159 non-null    object 
 21  데이터갱신일자   159 non-null    object 
 22  업태구분명     159 non-null    object 
 23  좌표정보(X)   159 non-null    float64
 24  좌표정보(Y)   159 non-null    float64
 25  점포구분명     104 non-null    object 
dtypes: float64(10), int64(5), object(11)
memory usage: 33.5+ KB


# 필요 항목만 추출
df_mart03 = df_mart02[['관리번호', '소재지면적', '사업장명', '업태구분명', '좌표정보(X)', '좌표정보(Y)'  ]]
df_mart03.columns = ['mart_id', 'mart_area', 'mart_nm', 'mart_ty', 'mart_x', 'mart_y']
df_mart03.info()
df_mart03.head()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 159 entries, 0 to 935
Data columns (total 6 columns):
 #   Column     Non-Null Count  Dtype  
---  ------     --------------  -----  
 0   mart_id    159 non-null    int64  
 1   mart_area  159 non-null    float64
 2   mart_nm    159 non-null    object 
 3   mart_ty    159 non-null    object 
 4   mart_x     159 non-null    float64
 5   mart_y     159 non-null    float64
dtypes: float64(3), int64(1), object(2)
memory usage: 8.7+ KB


# 마트 공간데이터화 
df_mart_geom = gpd.points_from_xy(df_mart03.mart_x, df_mart03.mart_y)
columns = df_mart03.columns
gdf_mart2097 = gpd.GeoDataFrame(df_mart03[columns], geometry=df_mart_geom, crs=from_epsg(2097))
gdf_mart4326 = gdf_mart2097.to_crs(epsg=4326)
gdf_mart3857 = gdf_mart5179.to_crs(epsg=3857)

C:\Users\dhl\AppData\Roaming\Python\Python38\site-packages\pyproj\crs\crs.py:53: FutureWarning: '+init=<authority>:<code>' syntax is deprecated. '<authority>:<code>' is the preferred initialization method. When making the change, be mindful of axis order changes: https://pyproj4.github.io/pyproj/stable/gotchas.html#axis-order-changes-in-proj-6
  return _prepare_from_string(" ".join(pjargs))


# 마트 위치 확인용 
ax = gdf_mart3857.plot(markersize=7, figsize=(10, 10))
ctx.add_basemap(ax, source=ctx.sources.ST_TERRAIN)  #ctx.sources.ST_TONER_LITE
ax.set_axis_off()
plt.show()

<ipython-input-137-37ce67be6df6>:3: FutureWarning: The "contextily.tile_providers" module is deprecated and will be removed in contextily v1.1. Please use "contextily.providers" instead.
  ctx.add_basemap(ax, source=ctx.sources.ST_TERRAIN)  #ctx.sources.ST_TONER_LITE


# Geometry를 이용하여 마트의 X, Y 좌표 항목을 생성 
gdf_mart4326["mart_lon"] = gdf_mart4326.geometry.x
gdf_mart4326["mart_lat"] = gdf_mart4326.geometry.y


# 집계구 공간데이터(shp) 로딩
gdf_jip5179 = gpd.read_file('data/admin_sl_2016/집계구.shp')
gdf_jip5179.info()
gdf_jip5179.head(3)

<class 'geopandas.geodataframe.GeoDataFrame'>
RangeIndex: 19153 entries, 0 to 19152
Data columns (total 4 columns):
 #   Column      Non-Null Count  Dtype   
---  ------      --------------  -----   
 0   TOT_REG_CD  19153 non-null  object  
 1   ADM_NM      19153 non-null  object  
 2   ADM_CD      19153 non-null  object  
 3   geometry    19153 non-null  geometry
dtypes: geometry(1), object(3)
memory usage: 598.7+ KB


gdf_jip5179.crs = "epsg:5179"
gdf_jip3857 = gdf_jip5179.to_crs(epsg=3857)
gdf_jip4326 = gdf_jip5179.to_crs(epsg=4326)


ax = gdf_jip3857.plot(color='gray', figsize=(12, 12), alpha=0.6)
ctx.add_basemap(ax, source=ctx.sources.ST_TERRAIN)  #ctx.sources.ST_TONER_LITE
ax.set_axis_off()
plt.show()

<ipython-input-13-1af1b8e2140b>:2: FutureWarning: The "contextily.tile_providers" module is deprecated and will be removed in contextily v1.1. Please use "contextily.providers" instead.
  ctx.add_basemap(ax, source=ctx.sources.ST_TERRAIN)  #ctx.sources.ST_TONER_LITE


# 7월15일 집계구별 생활인구 데이터 로딩
df_pop01 = pd.read_csv('data/LOCAL_PEOPLE_20210715.csv', encoding='cp949', header=0,
                      names=['dt', 'hour', 'hdong', 'TOT_REG_CD', 'pop_all', 'm0', 'm10', 'm15', 'm20', 'm25', 'm30', 'm35', 'm40', 'm45', 'm50', 'm55', 'm60', 'm65', 'm70', 'w0', 'w10', 'w15', 'w20', 'w25', 'w30', 'w35', 'w40', 'w45', 'w50', 'w55', 'w60', 'w65', 'w70'],
                      usecols=['hour', 'TOT_REG_CD', 'pop_all'],
                      dtype={'hour':float, 'TOT_REG_CD':object, 'pop_all':float}
                     )
df_pop01.head(3)


# 10시~ 20시 사이의 총생활인구(pop_all)을 합산하여 사용
df_pop02 = df_pop01[ (df_pop01.hour >= 10) & (df_pop01.hour <= 20) ]


df_pop03 = df_pop02.groupby(['TOT_REG_CD'])['pop_all'].sum().reset_index()
df_pop03['TOT_REG_CD'] = df_pop03.TOT_REG_CD.astype('object') 
df_pop03.info()
df_pop03.head()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 18953 entries, 0 to 18952
Data columns (total 2 columns):
 #   Column      Non-Null Count  Dtype  
---  ------      --------------  -----  
 0   TOT_REG_CD  18953 non-null  object 
 1   pop_all     18953 non-null  float64
dtypes: float64(1), object(1)
memory usage: 296.3+ KB


# 집계구 공간데이터에 집계구별 생활인구수를 속성조인
gdf_jip4326m = pd.merge(gdf_jip4326, df_pop03, on='TOT_REG_CD', how='left')
gdf_jip3857m = pd.merge(gdf_jip3857, df_pop03, on='TOT_REG_CD', how='left')
gdf_jip4326m.tail()


# 10~20시 집계구별 생활인구수 단계구분도
ax = gdf_jip3857m.plot(column='pop_all', scheme='Fisher_Jenks', k=5, cmap='Oranges_r', figsize=(15, 15), alpha=0.7)
ctx.add_basemap(ax, source=ctx.sources.ST_TONER_LITE)  #ctx.sources.ST_TONER_LITE
ax.set_axis_off()
plt.show()

<ipython-input-18-4e849bace3ce>:3: FutureWarning: The "contextily.tile_providers" module is deprecated and will be removed in contextily v1.1. Please use "contextily.providers" instead.
  ctx.add_basemap(ax, source=ctx.sources.ST_TONER_LITE)  #ctx.sources.ST_TONER_LITE


# Geometry를 이용하여 중심점의 X, Y 좌표 항목을 생성 
gdf_jip4326m_pt = gdf_jip4326m.copy()
gdf_jip4326m_pt['geometry'] = gdf_jip4326m_pt['geometry'].centroid
gdf_jip4326m_pt["jip_lon"] = gdf_jip4326m_pt.geometry.x
gdf_jip4326m_pt["jip_lat"] = gdf_jip4326m_pt.geometry.y
gdf_jip4326m_pt.head()

<ipython-input-39-0f00ed413452>:3: UserWarning: Geometry is in a geographic CRS. Results from 'centroid' are likely incorrect. Use 'GeoSeries.to_crs()' to re-project geometries to a projected CRS before this operation.

  gdf_jip4326m_pt['geometry'] = gdf_jip4326m_pt['geometry'].centroid


# cross join geopandas - 데이터가 너무 크면 문제될 수 있음 
gdf_jip4326m_pt['key'] = 1
gdf_mart4326['key'] = 1
merged = gdf_jip4326m_pt.merge(gdf_mart4326, on='key')


# 집계구와 마트간 직선거리 산출 - 이중 반복문을 쓰지 않아도 됨 
merged['dist'] = merged.apply(lambda x: great_circle((x['jip_lat'], x['jip_lon']), (x['mart_lat'], x['mart_lon'])).kilometers, axis=1)


merged.shape

(3045327, 18)


merged.head()


# 중력모델 기반 매력도(attract) 항목 산출 - 매장 면적 / 거리의 제곱 
merged['attract'] = merged.apply(lambda x: x['mart_area'] / math.pow(x['dist'], 2), axis=1)


merged.head()


# 중력모델 값 확인용
#merged_part = merged[  merged.TOT_REG_CD == 1101053010006 ]
#merged_part.to_csv("data/merged.csv", encoding='euc-kr')


# 집계구별로 마트 매력도가 가장 큰값만 추출
merged2 = merged.groupby('TOT_REG_CD')['attract'].agg(**{'attract':'max'}).reset_index()
# 아래 코드로 해도 될 것으로 예상.어느 게 더 성능이 좋을지는...
#merged.sort_values('attract').drop_duplicates(['TOT_REG_CD'],keep='last')


merged2.info()
merged2.head()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 19153 entries, 0 to 19152
Data columns (total 2 columns):
 #   Column      Non-Null Count  Dtype  
---  ------      --------------  -----  
 0   TOT_REG_CD  19153 non-null  object 
 1   attract     19153 non-null  float64
dtypes: float64(1), object(1)
memory usage: 299.4+ KB


# 매력도를 표준화
from sklearn.preprocessing import StandardScaler
merged2['attract_sc1'] = StandardScaler().fit_transform(merged2[['attract']])
merged2.head()


merged2['attract_sc1'].describe()

count    1.915300e+04
mean     3.372028e-17
std      1.000026e+00
min     -7.256842e-02
25%     -6.841745e-02
50%     -6.332803e-02
75%     -4.839055e-02
max      5.894172e+01
Name: attract_sc1, dtype: float64


# 표준화 매력도를 정규화
from sklearn.preprocessing import MinMaxScaler  #0~1로 정규화
merged2['attract_sc2'] = MinMaxScaler().fit_transform(merged2[['attract_sc1']])  
merged2.head()


merged2.attract_sc2.describe()

count    19153.000000
mean         0.001230
std          0.016945
min          0.000000
25%          0.000070
50%          0.000157
75%          0.000410
max          1.000000
Name: attract_sc2, dtype: float64


plt.boxplot(merged2.attract_sc2)
plt.show()


# 집계구 폴리곤에 중력모델 결과를 속성조인
gdf_jip3857m2 = pd.merge(gdf_jip3857m, merged2, on='TOT_REG_CD')
gdf_jip3857m2.info()

<class 'geopandas.geodataframe.GeoDataFrame'>
Int64Index: 19153 entries, 0 to 19152
Data columns (total 9 columns):
 #   Column       Non-Null Count  Dtype   
---  ------       --------------  -----   
 0   TOT_REG_CD   19153 non-null  object  
 1   ADM_NM       19153 non-null  object  
 2   ADM_CD       19153 non-null  object  
 3   geometry     19153 non-null  geometry
 4   pop_all      18953 non-null  float64 
 5   dist         150 non-null    float64 
 6   attract      19153 non-null  float64 
 7   attract_sc1  19153 non-null  float64 
 8   attract_sc2  19153 non-null  float64 
dtypes: float64(5), geometry(1), object(3)
memory usage: 1.5+ MB


gdf_jip3857m2.head()


gdf_jip3857m3 = gdf_jip3857m2[['TOT_REG_CD', 'ADM_NM', 'ADM_CD', 'geometry', 'pop_all', 'attract', 'attract_sc1', 'attract_sc2']]


gdf_jip3857m3.head()


# 집계구 폴리곤에 attract를 key로 한번 더 중력모델 결과를 속성조인
gdf_jip3857m4 = pd.merge(gdf_jip3857m3, merged, on='attract', how='left')
gdf_jip3857m4.info()
gdf_jip3857m4.head()

<class 'geopandas.geodataframe.GeoDataFrame'>
Int64Index: 19212 entries, 0 to 19211
Data columns (total 26 columns):
 #   Column        Non-Null Count  Dtype   
---  ------        --------------  -----   
 0   TOT_REG_CD_x  19212 non-null  object  
 1   ADM_NM_x      19212 non-null  object  
 2   ADM_CD_x      19212 non-null  object  
 3   geometry      19212 non-null  geometry
 4   pop_all_x     19012 non-null  float64 
 5   attract       19212 non-null  float64 
 6   attract_sc1   19212 non-null  float64 
 7   attract_sc2   19212 non-null  float64 
 8   TOT_REG_CD_y  19212 non-null  object  
 9   ADM_NM_y      19212 non-null  object  
 10  ADM_CD_y      19212 non-null  object  
 11  geometry_x    19212 non-null  geometry
 12  pop_all_y     19012 non-null  float64 
 13  jip_lon       19212 non-null  float64 
 14  jip_lat       19212 non-null  float64 
 15  dist          19212 non-null  float64 
 16  key           19212 non-null  int64   
 17  mart_id       19212 non-null  int64   
 18  mart_area     19212 non-null  float64 
 19  mart_nm       19212 non-null  object  
 20  mart_ty       19212 non-null  object  
 21  mart_x        19212 non-null  float64 
 22  mart_y        19212 non-null  float64 
 23  geometry_y    19212 non-null  geometry
 24  mart_lon      19212 non-null  float64 
 25  mart_lat      19212 non-null  float64 
dtypes: float64(13), geometry(3), int64(2), object(8)
memory usage: 4.0+ MB


gdf_jip3857m5 = gdf_jip3857m4[['TOT_REG_CD_x', 'ADM_NM_x', 'ADM_CD_x', 'geometry', 'pop_all_x', 'attract', 'attract_sc1', 'attract_sc2', 'dist', 'mart_id', 'mart_area', 'mart_nm']]
gdf_jip3857m5.columns = ['tot_reg_cd', 'adm_nm', 'adm_cd', 'geometry', 'pop_all', 'attract', 'attract_sc1', 'attract_sc2', 'dist', 'mart_id', 'mart_area', 'mart_nm']
gdf_jip3857m5.head()


gdf_jip3857m5.tail()


# 결과물 시각화
ax = gdf_jip3857m5.plot(column='attract', scheme='quantiles', k=5, cmap='Oranges', figsize=(15, 15), alpha=0.7)
ctx.add_basemap(ax, source=ctx.sources.ST_TONER_LITE)  #ctx.sources.ST_TONER_LITE
ax.set_axis_off()
plt.show()

<ipython-input-196-7ba5bc74e375>:3: FutureWarning: The "contextily.tile_providers" module is deprecated and will be removed in contextily v1.1. Please use "contextily.providers" instead.
  ctx.add_basemap(ax, source=ctx.sources.ST_TONER_LITE)  #ctx.sources.ST_TONER_LITE


# SHP 저장 
gdf_jip3857m5.to_file('data/gdf_jip3857m5.shp', encoding='euc-kr')

<ipython-input-197-572163a92dbe>:2: UserWarning: Column names longer than 10 characters will be truncated when saved to ESRI Shapefile.
  gdf_jip3857m5.to_file('data/gdf_jip3857m5.shp', encoding='euc-kr')


# 마트 명칭으로 디졸브 
gdf_jip3857_mart = gdf_jip3857m5.dissolve(by='mart_nm')
gdf_jip3857_mart.to_file('data/gdf_jip3857_mart.shp', encoding='euc-kr')

<ipython-input-198-044dfc34b7bb>:3: UserWarning: Column names longer than 10 characters will be truncated when saved to ESRI Shapefile.
  gdf_jip3857_mart.to_file('data/gdf_jip3857_mart.shp', encoding='euc-kr')


gdf_mart4326.to_file('data/gdf_mart4326.shp', encoding='euc-kr')
gdf_mart3857.to_file('data/gdf_mart3857.shp', encoding='euc-kr')

	개방자치단체코드	관리번호	인허가일자	인허가취소일자	영업상태코드	영업상태명	상세영업상태코드	상세영업상태명	폐업일자	휴업시작일자	...	도로명주소	도로명우편번호	사업장명	최종수정일자	데이터갱신구분	데이터갱신일자	업태구분명	좌표정보(X)	좌표정보(Y)	점포구분명
0	3000000	2019300020207500001	20190917	NaN	1	영업/정상	1	정상영업	NaN	NaN	...	서울특별시 종로구 삼일대로 428 낙원상가 506호 (낙원동)	3140.0	낙원상가	20190925150602	U	2019-09-27 02:40:00.0	그 밖의 대규모점포	198838.912966	452214.210962	대규모점포
1	3000000	2019300020207500002	20190917	NaN	1	영업/정상	1	정상영업	NaN	NaN	...	서울특별시 종로구 삼일대로 428 낙원상가 (낙원동)	3140.0	낙원상가	20190925150506	I	2019-09-27 02:22:37.0	그 밖의 대규모점포	198838.912966	452214.210962	대규모점포

	개방자치단체코드	관리번호	인허가일자	인허가취소일자	영업상태코드	영업상태명	상세영업상태코드	상세영업상태명	폐업일자	휴업시작일자	...	도로명주소	도로명우편번호	사업장명	최종수정일자	데이터갱신구분	데이터갱신일자	업태구분명	좌표정보(X)	좌표정보(Y)	점포구분명
0	3000000	2019300020207500001	20190917	NaN	1	영업/정상	1	정상영업	NaN	NaN	...	서울특별시 종로구 삼일대로 428 낙원상가 506호 (낙원동)	3140.0	낙원상가	20190925150602	U	2019-09-27 02:40:00.0	그 밖의 대규모점포	198838.912966	452214.210962	대규모점포
1	3000000	2019300020207500002	20190917	NaN	1	영업/정상	1	정상영업	NaN	NaN	...	서울특별시 종로구 삼일대로 428 낙원상가 (낙원동)	3140.0	낙원상가	20190925150506	I	2019-09-27 02:22:37.0	그 밖의 대규모점포	198838.912966	452214.210962	대규모점포

	mart_id	mart_area	mart_nm	mart_ty	mart_x	mart_y
0	2019300020207500001	25198.02	낙원상가	그 밖의 대규모점포	198838.912966	452214.210962
1	2019300020207500002	25198.02	낙원상가	그 밖의 대규모점포	198838.912966	452214.210962
2	2003300012907500001	16128.75	광장주식회사	시장	199837.414267	451974.128468
6	2004300007607500018	11750.00	동대문종합시장D동상가	그 밖의 대규모점포	200579.409755	452035.347659
13	2012300012907500001	16128.75	광장시장	복합쇼핑몰	199837.414267	451974.128468

	hour	TOT_REG_CD	pop_all
0	17.0	1115060030401	153.4582
1	1.0	1115060040001	3.9789
2	9.0	1110060020003	10.7129

	TOT_REG_CD	pop_all
0	1101053010001	3828.8897
1	1101053010002	20118.0878
2	1101053010003	22248.8882
3	1101053010004	21798.5802
4	1101053010005	16343.3748

중력모델 기반 영향권 분석¶

데이터¶

로직¶

데이터 로딩 및 전처리¶

포인트 데이터 - 서울특별시 대규모점포 인허가 정보¶

폴리곤 데이터 - 서울시 생활인구 (집계구별)¶

근린 분석¶

중력모델 산출¶

	TOT_REG_CD	ADM_NM	ADM_CD	geometry
0	1101053010006	사직동	1101053	POLYGON ((953231.968 1953435.866, 953237.202 1...
1	1101053010001	사직동	1101053	POLYGON ((952858.566 1952976.274, 952875.055 1...
2	1101053010003	사직동	1101053	POLYGON ((952889.178 1953405.246, 952890.836 1...

	TOT_REG_CD	ADM_NM	ADM_CD	geometry	pop_all
19148	1102073010501	동화동	1102073	POLYGON ((127.01764 37.56250, 127.01763 37.562...	1221.9702
19149	1102055030001	명동	1102055	POLYGON ((126.98893 37.56810, 126.98895 37.568...	121202.7230
19150	1102058040004	장충동	1102058	POLYGON ((127.00338 37.55903, 127.00344 37.559...	48856.1133
19151	1121052010002	보라매동	1121052	POLYGON ((126.92720 37.49429, 126.92709 37.493...	23755.7097
19152	1121052010001	보라매동	1121052	POLYGON ((126.92591 37.49144, 126.92596 37.491...	29766.9029

	TOT_REG_CD	attract
0	1101053010001	25032.015982
1	1101053010002	23781.495017
2	1101053010003	20374.563266
3	1101053010004	29197.524019
4	1101053010005	25115.623315

	TOT_REG_CD	attract	attract_sc1
0	1101053010001	25032.015982	-0.062702
1	1101053010002	23781.495017	-0.063221
2	1101053010003	20374.563266	-0.064637
3	1101053010004	29197.524019	-0.060970
4	1101053010005	25115.623315	-0.062667

	tot_reg_cd	adm_nm	adm_cd	geometry	pop_all	attract	attract_sc1	attract_sc2	dist	mart_id	mart_area	mart_nm
19207	1102073010501	동화동	1102073	POLYGON ((14139538.793 4517804.641, 14139537.7...	1221.9702	63946.892311	-0.046528	0.000441	0.473384	2002301007107500008	14330.00	서울중앙시장
19208	1102055030001	명동	1102055	POLYGON ((14136342.720 4518591.610, 14136344.7...	121202.7230	101597.255067	-0.030880	0.000706	0.768351	2012301010007500002	59979.25	롯데백화점 본점
19209	1102058040004	장충동	1102058	POLYGON ((14137952.117 4517316.775, 14137958.7...	48856.1133	16165.854358	-0.066387	0.000105	1.578934	2008301010007500005	40302.01	굿모닝시티 쇼핑몰
19210	1121052010002	보라매동	1121052	POLYGON ((14129470.918 4508229.718, 14129459.5...	23755.7097	128762.123348	-0.019590	0.000898	0.410626	2012320019107500002	21711.05	롯데쇼핑(주) 관악점
19211	1121052010001	보라매동	1121052	POLYGON ((14129327.270 4507830.057, 14129333.2...	29766.9029	281075.067367	0.043714	0.001970	0.277926	2012320019107500002	21711.05	롯데쇼핑(주) 관악점

	TOT_REG_CD	ADM_NM	ADM_CD	geometry	pop_all	jip_lon	jip_lat
0	1101053010006	사직동	1101053	POINT (126.97031 37.57830)	4423.9508	126.970311	37.578304
1	1101053010001	사직동	1101053	POINT (126.96518 37.57415)	3828.8897	126.965178	37.574151
2	1101053010003	사직동	1101053	POINT (126.96551 37.57651)	22248.8882	126.965513	37.576513
3	1101053010002	사직동	1101053	POINT (126.96900 37.57709)	20118.0878	126.969002	37.577092
4	1101053010005	사직동	1101053	POINT (126.97277 37.57803)	16343.3748	126.972772	37.578025

	TOT_REG_CD	ADM_NM	ADM_CD	geometry_x	pop_all	jip_lon	jip_lat	dist	key	mart_id	mart_area	mart_nm	mart_ty	mart_x	mart_y	geometry_y	mart_lon	mart_lat	attract
0	1101053010006	사직동	1101053	POINT (126.97031 37.57830)	4423.9508	126.970311	37.578304	5.478750	1	2004302007407500001	117912.81	아이파크몰(I PARK MALL)	쇼핑센터	196762.077395	447480.039577	POINT (126.96127 37.52956)	126.961267	37.529557	3928.239647
1	1101053010006	사직동	1101053	POINT (126.97031 37.57830)	4423.9508	126.970311	37.578304	2.072085	1	2010301010007500002	12585.13	신세계백화점메사점	쇼핑센터	198129.435543	450900.239718	POINT (126.97673 37.56038)	126.976727	37.560377	2931.181501
2	1101053010006	사직동	1101053	POINT (126.97031 37.57830)	4423.9508	126.970311	37.578304	3.621467	1	2010301010007500003	8119.00	올레오	쇼핑센터	201040.352596	451852.142613	POINT (127.00967 37.56896)	127.009674	37.568955	619.061011
3	1101053010006	사직동	1101053	POINT (126.97031 37.57830)	4423.9508	126.970311	37.578304	1.653768	1	2012301010007500002	59979.25	롯데백화점 본점	백화점	198259.653577	451392.198219	POINT (126.97820 37.56481)	126.978200	37.564810	21930.676029
4	1101053010006	사직동	1101053	POINT (126.97031 37.57830)	4423.9508	126.970311	37.578304	2.470420	1	2012301010007500004	11576.19	롯데아울렛 서울역점	쇼핑센터	197230.206090	450446.684396	POINT (126.96655 37.55629)	126.966551	37.556288	1896.810663